1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
|
#include <vector>
#include "caffe/filler.hpp"
#include "caffe/layer.hpp"
#include "caffe/util/im2col.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/vision_layers.hpp"
namespace caffe {
template <typename Dtype>
void ConvolutionLayer<Dtype>::Forward_gpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
const Dtype* weight = this->blobs_[0]->gpu_data();
for (int i = 0; i < bottom.size(); ++i) {
const Dtype* bottom_data = bottom[i]->gpu_data();
Dtype* top_data = top[i]->mutable_gpu_data();
for (int n = 0; n < this->num_; ++n) {
this->forward_gpu_gemm(bottom_data + bottom[i]->offset(n), weight,
top_data + top[i]->offset(n));
if (this->bias_term_) {
const Dtype* bias = this->blobs_[1]->gpu_data();
this->forward_gpu_bias(top_data + top[i]->offset(n), bias);
}
}
}
}
template <typename Dtype>
void ConvolutionLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
const Dtype* weight = this->blobs_[0]->gpu_data();
Dtype* weight_diff = this->blobs_[0]->mutable_gpu_diff();
for (int i = 0; i < top.size(); ++i) {
const Dtype* top_diff = top[i]->gpu_diff();
// Bias gradient, if necessary.
if (this->bias_term_ && this->param_propagate_down_[1]) {
Dtype* bias_diff = this->blobs_[1]->mutable_gpu_diff();
for (int n = 0; n < this->num_; ++n) {
this->backward_gpu_bias(bias_diff, top_diff + top[i]->offset(n));
}
}
if (this->param_propagate_down_[0] || propagate_down[i]) {
const Dtype* bottom_data = bottom[i]->gpu_data();
Dtype* bottom_diff = bottom[i]->mutable_gpu_diff();
for (int n = 0; n < this->num_; ++n) {
// gradient w.r.t. weight. Note that we will accumulate diffs.
if (this->param_propagate_down_[0]) {
this->weight_gpu_gemm(bottom_data + bottom[i]->offset(n),
top_diff + top[i]->offset(n), weight_diff);
}
// gradient w.r.t. bottom data, if necessary.
if (propagate_down[i]) {
this->backward_gpu_gemm(top_diff + top[i]->offset(n), weight,
bottom_diff + bottom[i]->offset(n));
}
}
}
}
}
INSTANTIATE_LAYER_GPU_FUNCS(ConvolutionLayer);
} // namespace caffe
|
